← 返回 Skills 市场
Tool 1:
Tool 2:
Jinko
作者
kevinjinko
· GitHub ↗
· v1.0.0
2551
总下载
1
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install jinko-flight-search
功能描述
Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com.
使用说明 (SKILL.md)
Jinko Flight Search
Search flights and discover destinations via the Jinko MCP server (find_destination and find_flight tools).
MCP Connection
Connect the Jinko MCP server in Claude's settings or project integrations using this URL:
https://mcp.gojinko.com
This provides two tools: Jinko:find_destination and Jinko:find_flight.
Tool Selection
- User knows origin AND destination city → Use
find_flight - User wants destination ideas, doesn't know where to go, or specifies criteria (beach, warm, ski, cheap…) → Use
find_destination - User asks for the cheapest dates to a single known destination → Use
find_flight
Tool 1: find_destination — Discover Where to Go
Use when the user is exploring options and hasn't committed to a single destination city.
Required Parameters
origins— Array of IATA codes for ALL nearby airports at the user's origin.trip_type—"roundtrip"(default) or"oneway"(only when user explicitly says one-way).
Optional Parameters
| Parameter | Use when |
|---|---|
destinations |
User mentions a region, criteria, or list of candidate cities. Generate IATA codes matching the intent. Leave empty for global discovery ("anywhere", "surprise me"). |
departure_dates / departure_date_ranges |
User specifies dates or periods. All dates MUST be in the future. |
return_dates / return_date_ranges |
User specifies return windows. |
stay_days / stay_days_range |
User mentions trip length ("a week", "5-10 days"). |
max_price |
User mentions a budget. |
direct_only |
User asks for nonstop/direct flights. |
cabin_class |
"economy", "premium_economy", "business", or "first". |
currency |
ISO 4217 code matching user's locale. |
locale |
e.g. "en-US", "fr-FR". |
sort_by |
"lowest" (default) or "recommendation". |
Airport Identification — Critical
Always expand a city to ALL its airports:
- New York →
["JFK","LGA","EWR"] - London →
["LHR","LGW","STN","LTN","LCY"] - Paris →
["CDG","ORY"] - Tokyo →
["NRT","HND"] - Chicago →
["ORD","MDW"] - Los Angeles →
["LAX"] - San Francisco / SFO →
["SFO"]
Destination Generation — Critical
When users describe criteria, generate matching IATA codes before calling the tool:
- "Beach" →
["MIA","SAN","HNL","CUN","PUJ","SJU","NAS","MBJ"] - "Asia" →
["NRT","HND","ICN","PVG","PEK","HKG","SIN","BKK","KUL","MNL"] - "European capitals" →
["LHR","CDG","FRA","MAD","FCO","AMS","BRU","VIE","PRG","CPH"] - "Ski" →
["DEN","SLC","ZRH","INN","GVA","TRN"] - "Warm in winter" →
["MIA","MCO","SAN","PHX","HNL","CUN","PUJ","PTY","LIM","GIG"]
When to Re-call
Re-call find_destination when the user changes destination criteria, dates, or asks to explore different options — especially when they are already viewing the widget in fullscreen.
Examples
| User says | origins | destinations | other params |
|---|---|---|---|
| "Where should I travel from NYC next month?" | ["JFK","LGA","EWR"] |
[] (global) |
departure_date_ranges for next month |
| "Cheap flights from SF to Europe under $800" | ["SFO"] |
European airports | max_price: 800 |
| "Somewhere warm from Chicago, 1 week in Dec" | ["ORD","MDW"] |
warm-weather airports | stay_days: 7, Dec date range |
| "Best weekend getaways from Boston" | ["BOS"] |
[] (global) |
stay_days_range: {min:2, max:4} |
Tool 2: find_flight — Search a Specific Route
Use when both origin and destination cities are known.
Required Parameters
origin— Single IATA airport or city code (e.g."JFK","PAR").destination— Single IATA airport or city code (e.g."CDG","LON").trip_type—"roundtrip"(default) or"oneway".
Optional Parameters
Same date, stay, price, cabin, currency, locale, direct, and sort parameters as find_destination.
Examples
| User says | origin | destination | other params |
|---|---|---|---|
| "Flights from JFK to CDG next month" | "JFK" |
"CDG" |
departure_date_ranges for next month |
| "LA to Tokyo for a week in December" | "LAX" |
"TYO" |
stay_days: 7, Dec date range |
| "Business class NYC to London, 5-10 days" | "NYC" |
"LON" |
cabin_class: "business", stay_days_range: {min:5, max:10} |
| "Cheapest ORD to LHR under $600" | "ORD" |
"LHR" |
max_price: 600 |
General Rules
- Default to roundtrip. Only use
"oneway"when the user explicitly writes "one way" or "one-way". - All dates must be in the future. Never send a past date.
- Fill as many search parameters as possible from the user's intent to get the best results.
- Use city codes (e.g.
"LON","NYC","PAR","TYO") when searching across all airports in a city. - Provide results in the user's preferred currency and locale when identifiable.
安全使用建议
This skill appears internally consistent for searching flights via an external Jinko MCP server. Before installing or enabling it: (1) verify the external endpoint (https://mcp.gojinko.com) and the publisher/source since no homepage or owner metadata is provided; (2) confirm whether the MCP integration requires API keys/tokens and where those credentials are stored (agent settings/integrations) — the SKILL.md does not describe authentication; (3) avoid providing sensitive personal or payment information through the skill unless you trust the service and understand its privacy policies; and (4) if you need higher assurance, ask the publisher for a homepage, documentation, or contact info.
功能分析
Type: OpenClaw Skill
Name: jinko-flight-search
Version: 1.0.0
The skill bundle is benign. It clearly defines its purpose as flight search and destination discovery, relying on an explicitly stated external server at `https://mcp.gojinko.com`. The `SKILL.md` provides detailed, but legitimate, instructions for the AI agent on how to interpret user requests and map them to parameters for the `find_destination` and `find_flight` tools. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts designed to subvert the agent's security or intended function.
能力评估
Purpose & Capability
The name/description match the instructions: the SKILL.md describes two tools (find_destination, find_flight) and shows parameters and examples for flight discovery and route searches. The required actions (expanding cities to airport IATA codes, building search params, calling the MCP tools) are appropriate for a flight-search capability.
Instruction Scope
Instructions are narrowly scoped to composing flight-search queries, generating airport/IATA lists, and calling the MCP endpoint. The SKILL.md does not instruct reading local files, shell history, system credentials, or sending data to unrelated external endpoints.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing will be written to disk or installed by the skill. This is the lowest-risk install profile.
Credentials
The skill declares no required environment variables or credentials, which is proportionate for an instruction-only tool. However, it expects the agent/project to be connected to an external MCP server (https://mcp.gojinko.com) via Claude's settings/integrations; the SKILL.md does not document whether authentication (API keys, tokens) is required or where those credentials would be stored. Verify how the MCP integration is authenticated and whether any secrets are configured outside the skill.
Persistence & Privilege
always is false, the skill is user-invocable, and there is no instruction to alter agent configurations or other skills. It does not request permanent presence or elevated platform privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install jinko-flight-search - 安装完成后，直接呼叫该 Skill 的名称或使用
/jinko-flight-search触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of Jinko Flight Search skill.
- Supports destination discovery based on user criteria (budget, activities, climate, etc.) via `find_destination`.
- Provides specific flight search and comparison between known cities or airports with `find_flight`.
- Includes flexible options: date ranges, stay length, cabin class, budget, and more.
- Handles city-to-multi-airport conversion and destination criteria mapping.
- Requires connection to the Jinko MCP server at https://mcp.gojinko.com for all operations.
元数据
常见问题
Jinko 是什么？
Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2551 次。
如何安装 Jinko？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install jinko-flight-search」即可一键安装，无需额外配置。
Jinko 是免费的吗？
是的，Jinko 完全免费（开源免费），可自由下载、安装和使用。
Jinko 支持哪些平台？
Jinko 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Jinko？
由 kevinjinko（@kevinjinko）开发并维护，当前版本 v1.0.0。
推荐 Skills